End of training

README.md

@@ -1,13 +1,28 @@
 ---
 library_name: transformers
+language:
+- en
 base_model: Hartunka/tiny_bert_rand_50_v2
 tags:
 - generated_from_trainer
+datasets:
+- glue
 metrics:
 - spearmanr
 model-index:
 - name: tiny_bert_rand_50_v2_stsb
-  results: []
+  results:
+  - task:
+      name: Text Classification
+      type: text-classification
+    dataset:
+      name: GLUE STSB
+      type: glue
+      args: stsb
+    metrics:
+    - name: Spearmanr
+      type: spearmanr
+      value: 0.25802571079319986
 ---
 
 <!-- This model card has been generated automatically according to the information the Trainer had access to. You
@@ -15,12 +30,12 @@ should probably proofread and complete it, then remove this comment. -->
 
 # tiny_bert_rand_50_v2_stsb
 
-This model is a fine-tuned version of [Hartunka/tiny_bert_rand_50_v2](https://huggingface.co/Hartunka/tiny_bert_rand_50_v2) on an unknown dataset.
+This model is a fine-tuned version of [Hartunka/tiny_bert_rand_50_v2](https://huggingface.co/Hartunka/tiny_bert_rand_50_v2) on the GLUE STSB dataset.
 It achieves the following results on the evaluation set:
-- Loss: 3.0019
-- Pearson: 0.2613
-- Spearmanr: 0.2697
-- Combined Score: 0.2655
+- Loss: 2.2828
+- Pearson: 0.2634
+- Spearmanr: 0.2580
+- Combined Score: 0.2607
 
 ## Model description
 

all_results.json

@@ -0,0 +1,17 @@
+{
+    "epoch": 10.0,
+    "eval_combined_score": 0.26071507127769444,
+    "eval_loss": 2.282820701599121,
+    "eval_pearson": 0.263404431762189,
+    "eval_runtime": 0.473,
+    "eval_samples": 1500,
+    "eval_samples_per_second": 3171.07,
+    "eval_spearmanr": 0.25802571079319986,
+    "eval_steps_per_second": 12.684,
+    "total_flos": 1507548205378560.0,
+    "train_loss": 1.5338545426078465,
+    "train_runtime": 43.6565,
+    "train_samples": 5749,
+    "train_samples_per_second": 6584.362,
+    "train_steps_per_second": 26.342
+}

eval_results.json

@@ -0,0 +1,11 @@
+{
+    "epoch": 10.0,
+    "eval_combined_score": 0.26071507127769444,
+    "eval_loss": 2.282820701599121,
+    "eval_pearson": 0.263404431762189,
+    "eval_runtime": 0.473,
+    "eval_samples": 1500,
+    "eval_samples_per_second": 3171.07,
+    "eval_spearmanr": 0.25802571079319986,
+    "eval_steps_per_second": 12.684
+}

logs/events.out.tfevents.1745318727.s_005_m.2850172.49

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:29cf8266e4c7e1ae465771151d31957aa1a12653627621693b30c560e586bf95
+size 473

train_results.json

@@ -0,0 +1,9 @@
+{
+    "epoch": 10.0,
+    "total_flos": 1507548205378560.0,
+    "train_loss": 1.5338545426078465,
+    "train_runtime": 43.6565,
+    "train_samples": 5749,
+    "train_samples_per_second": 6584.362,
+    "train_steps_per_second": 26.342
+}

trainer_state.json

@@ -0,0 +1,232 @@
+{
+  "best_global_step": 115,
+  "best_metric": 2.282820701599121,
+  "best_model_checkpoint": "tiny_bert_rand_50_v2_stsb/checkpoint-115",
+  "epoch": 10.0,
+  "eval_steps": 500,
+  "global_step": 230,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 1.0,
+      "grad_norm": 4.757383823394775,
+      "learning_rate": 4.9e-05,
+      "loss": 3.577,
+      "step": 23
+    },
+    {
+      "epoch": 1.0,
+      "eval_combined_score": 0.11416083891115508,
+      "eval_loss": 2.3197340965270996,
+      "eval_pearson": 0.12061995262322296,
+      "eval_runtime": 0.4408,
+      "eval_samples_per_second": 3403.103,
+      "eval_spearmanr": 0.10770172519908719,
+      "eval_steps_per_second": 13.612,
+      "step": 23
+    },
+    {
+      "epoch": 2.0,
+      "grad_norm": 10.133877754211426,
+      "learning_rate": 4.8e-05,
+      "loss": 2.0557,
+      "step": 46
+    },
+    {
+      "epoch": 2.0,
+      "eval_combined_score": 0.12699515116533755,
+      "eval_loss": 2.4031293392181396,
+      "eval_pearson": 0.12910611175823888,
+      "eval_runtime": 0.5154,
+      "eval_samples_per_second": 2910.631,
+      "eval_spearmanr": 0.1248841905724362,
+      "eval_steps_per_second": 11.643,
+      "step": 46
+    },
+    {
+      "epoch": 3.0,
+      "grad_norm": 8.422947883605957,
+      "learning_rate": 4.7e-05,
+      "loss": 1.8854,
+      "step": 69
+    },
+    {
+      "epoch": 3.0,
+      "eval_combined_score": 0.2013417461648624,
+      "eval_loss": 2.3712551593780518,
+      "eval_pearson": 0.203885354732845,
+      "eval_runtime": 0.4923,
+      "eval_samples_per_second": 3047.172,
+      "eval_spearmanr": 0.19879813759687975,
+      "eval_steps_per_second": 12.189,
+      "step": 69
+    },
+    {
+      "epoch": 4.0,
+      "grad_norm": 11.295201301574707,
+      "learning_rate": 4.600000000000001e-05,
+      "loss": 1.7118,
+      "step": 92
+    },
+    {
+      "epoch": 4.0,
+      "eval_combined_score": 0.2468785884457752,
+      "eval_loss": 2.3257670402526855,
+      "eval_pearson": 0.24741486493265863,
+      "eval_runtime": 0.4527,
+      "eval_samples_per_second": 3313.331,
+      "eval_spearmanr": 0.24634231195889175,
+      "eval_steps_per_second": 13.253,
+      "step": 92
+    },
+    {
+      "epoch": 5.0,
+      "grad_norm": 6.806567668914795,
+      "learning_rate": 4.5e-05,
+      "loss": 1.4486,
+      "step": 115
+    },
+    {
+      "epoch": 5.0,
+      "eval_combined_score": 0.26071507127769444,
+      "eval_loss": 2.282820701599121,
+      "eval_pearson": 0.263404431762189,
+      "eval_runtime": 0.4792,
+      "eval_samples_per_second": 3130.148,
+      "eval_spearmanr": 0.25802571079319986,
+      "eval_steps_per_second": 12.521,
+      "step": 115
+    },
+    {
+      "epoch": 6.0,
+      "grad_norm": 8.495306968688965,
+      "learning_rate": 4.4000000000000006e-05,
+      "loss": 1.2898,
+      "step": 138
+    },
+    {
+      "epoch": 6.0,
+      "eval_combined_score": 0.26830817042733024,
+      "eval_loss": 2.7079834938049316,
+      "eval_pearson": 0.2622377772014732,
+      "eval_runtime": 0.4751,
+      "eval_samples_per_second": 3157.388,
+      "eval_spearmanr": 0.27437856365318725,
+      "eval_steps_per_second": 12.63,
+      "step": 138
+    },
+    {
+      "epoch": 7.0,
+      "grad_norm": 13.502508163452148,
+      "learning_rate": 4.3e-05,
+      "loss": 1.0578,
+      "step": 161
+    },
+    {
+      "epoch": 7.0,
+      "eval_combined_score": 0.28573879609613473,
+      "eval_loss": 2.650726318359375,
+      "eval_pearson": 0.28150603591850215,
+      "eval_runtime": 0.4542,
+      "eval_samples_per_second": 3302.865,
+      "eval_spearmanr": 0.2899715562737673,
+      "eval_steps_per_second": 13.211,
+      "step": 161
+    },
+    {
+      "epoch": 8.0,
+      "grad_norm": 7.592569351196289,
+      "learning_rate": 4.2e-05,
+      "loss": 0.8953,
+      "step": 184
+    },
+    {
+      "epoch": 8.0,
+      "eval_combined_score": 0.2609240583203716,
+      "eval_loss": 2.863307237625122,
+      "eval_pearson": 0.25851307223546727,
+      "eval_runtime": 0.5148,
+      "eval_samples_per_second": 2913.731,
+      "eval_spearmanr": 0.2633350444052759,
+      "eval_steps_per_second": 11.655,
+      "step": 184
+    },
+    {
+      "epoch": 9.0,
+      "grad_norm": 29.740528106689453,
+      "learning_rate": 4.1e-05,
+      "loss": 0.7584,
+      "step": 207
+    },
+    {
+      "epoch": 9.0,
+      "eval_combined_score": 0.2446564587157261,
+      "eval_loss": 3.175959587097168,
+      "eval_pearson": 0.24206257082189755,
+      "eval_runtime": 0.4631,
+      "eval_samples_per_second": 3238.968,
+      "eval_spearmanr": 0.24725034660955467,
+      "eval_steps_per_second": 12.956,
+      "step": 207
+    },
+    {
+      "epoch": 10.0,
+      "grad_norm": 10.117051124572754,
+      "learning_rate": 4e-05,
+      "loss": 0.6589,
+      "step": 230
+    },
+    {
+      "epoch": 10.0,
+      "eval_combined_score": 0.26549244920567694,
+      "eval_loss": 3.0019023418426514,
+      "eval_pearson": 0.26127781004194356,
+      "eval_runtime": 0.4522,
+      "eval_samples_per_second": 3316.9,
+      "eval_spearmanr": 0.2697070883694104,
+      "eval_steps_per_second": 13.268,
+      "step": 230
+    },
+    {
+      "epoch": 10.0,
+      "step": 230,
+      "total_flos": 1507548205378560.0,
+      "train_loss": 1.5338545426078465,
+      "train_runtime": 43.6565,
+      "train_samples_per_second": 6584.362,
+      "train_steps_per_second": 26.342
+    }
+  ],
+  "logging_steps": 1,
+  "max_steps": 1150,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 50,
+  "save_steps": 500,
+  "stateful_callbacks": {
+    "EarlyStoppingCallback": {
+      "args": {
+        "early_stopping_patience": 5,
+        "early_stopping_threshold": 0.0
+      },
+      "attributes": {
+        "early_stopping_patience_counter": 5
+      }
+    },
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": true,
+        "should_training_stop": true
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 1507548205378560.0,
+  "train_batch_size": 256,
+  "trial_name": null,
+  "trial_params": null
+}